Research on Lightweight Citrus Flowering Rate Statistical Model Combined with Anchor Frame Clustering Optimization

Lu, Jianqiang; Lin, Weize; Chen, Pingfu; Lan, Yubin; Deng, Xiaoling; Niu, Hongyu; Mo, Jiawei; Li, Jiaxing; Luo, Shengfu

doi:10.3390/s21237929

Cited by 3 publications

(2 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A combination of computer vision techniques and deep learning algorithms have been extensively employed in various fields of agricultural production, and numerous studies have demonstrated promising outcomes [17][18][19]. However, most existing studies on flower recognition only focused on identifying flower species and not flowering period recognition [20][21][22]. This study aims to find a lightweight and high-precision YOLO algorithm and attempts to improve it to be more suitable for use on inexpensive camera devices to identify and distinguish the flowering periods of yellow chrysanthemums.…”

Section: Introductionmentioning

confidence: 99%

Detection of Chrysanthemums Inflorescence Based on Improved CR-YOLOv5s Algorithm

Zhao

Zheng

2023

Sensors

View full text Add to dashboard Cite

Accurate recognition of the flowering stage is a prerequisite for flower yield estimation. In order to improve the recognition accuracy based on the complex image background, such as flowers partially covered by leaves and flowers with insignificant differences in various fluorescence, this paper proposed an improved CR-YOLOv5s to recognize flower buds and blooms for chrysanthemums by emphasizing feature representation through an attention mechanism. The coordinate attention mechanism module has been introduced to the backbone of the YOLOv5s so that the network can pay more attention to chrysanthemum flowers, thereby improving detection accuracy and robustness. Specifically, we replaced the convolution blocks in the backbone network of YOLOv5s with the convolution blocks from the RepVGG block structure to improve the feature representation ability of YOLOv5s through a multi-branch structure, further improving the accuracy and robustness of detection. The results showed that the average accuracy of the improved CR-YOLOv5s was as high as 93.9%, which is 4.5% better than that of normal YOLOv5s. This research provides the basis for the automatic picking and grading of flowers, as well as a decision-making basis for estimating flower yield.

show abstract

Section: Introductionmentioning

confidence: 99%

Detection of Chrysanthemums Inflorescence Based on Improved CR-YOLOv5s Algorithm

Zhao

Zheng

2023

Sensors

View full text Add to dashboard Cite

show abstract

“…Edge detection is an important process in techniques, such as image analysis and processing, computer vision and pattern recognition, with the aim of detecting information about the shape of objects in an image [1,2,3,4]. In the real world, there are four situations in which edges can be formed in an image: (1) discontinuities in depth, (2) discontinuities in surface orientation, (3) different materials of objects in an image, and (4) different lighting in a scene.…”

Section: Introductionmentioning

confidence: 99%

Research on Wavelet Transform Modulus Maxima and OTSU in Edge Detection

You¹,

Han²,

Liu³

et al. 2023

Preprint

View full text Add to dashboard Cite

In the course of routine bridge maintenance, edge detection allows the partial condition of the bridge to be viewed. However, many edge detection methods often have unsatisfactory performances when dealing with images with complex backgrounds. Moreover, the processing often involves the manual selection of thresholds, which can result in repeated testing and comparisons. To addresses these problems in this paper, the wavelet transform modulus maxima method is used to detect the target image, and then the threshold value of the image can be determined automatically according to the OTSU method to remove the pseudo-edges. Thus, the real image edges can be detected. The results show that the information entropy and SSIM of the detection results are the highest when compared with the commonly used Canny and Laplace algorithms, which means that the detection quality is optimal. To more fully illustrate the advantages of the algorithms, images with more complex backgrounds was detected, and the processing results of the algorithms in this paper are still optimal. In addition, the automatic selection of thresholds saves the operator's effort and improves the detection efficiency. Thanks to the combined use of the above two methods, detection quality and efficiency are significantly improved, which has a good application in engineering practice.

show abstract

Feasibility assessment of tree-level flower intensity quantification from UAV RGB imagery: A triennial study in an apple orchard

Zhang¹,

Valente²,

Wang³

et al. 2023

ISPRS Journal of Photogrammetry and Remote Sensing

View full text Add to dashboard Cite

Research on Lightweight Citrus Flowering Rate Statistical Model Combined with Anchor Frame Clustering Optimization

Cited by 3 publications

References 28 publications

Detection of Chrysanthemums Inflorescence Based on Improved CR-YOLOv5s Algorithm

Detection of Chrysanthemums Inflorescence Based on Improved CR-YOLOv5s Algorithm

Research on Wavelet Transform Modulus Maxima and OTSU in Edge Detection

Feasibility assessment of tree-level flower intensity quantification from UAV RGB imagery: A triennial study in an apple orchard

Contact Info

Product

Resources

About